Home Household machines Why home robots are so hard to build

Why home robots are so hard to build


Who wouldn’t want a robot to take care of all the household chores? Skathi/iStock via Getty Images

With recent advancements in artificial intelligence and robotics technology, there is growing interest in developing and commercializing home robots capable of handling a variety of household tasks.

Tesla is building a humanoid robot that CEO Elon Musk says could be used to cook meals and help the elderly. Amazon recently acquired iRobot, a major maker of robotic vacuum cleaners, and has invested heavily in the technology through the Amazon Robotics program to bring robotic technology to the consumer market. In May 2022, Dyson, a company renowned for its electric vacuum cleaners, announced plans to build the UK’s largest robotics center dedicated to the development of household robots that perform daily household tasks in residential spaces.

Despite the growing interest, potential customers may have to wait a while for these robots to hit the market. While devices such as smart thermostats and security systems are widely used in homes today, the commercial use of food processors is still in its infancy.

As a robotics researcher, I know firsthand how considerably more difficult household robots are to build than smart digital devices or industrial robots.

Object manipulation

A major difference between digital and robotic devices is that home robots must manipulate objects through physical contact to perform their tasks. They have to carry the plates, move the chairs and pick up the dirty laundry and put it in the washing machine. These operations require the robot to be able to handle fragile, soft and sometimes heavy objects with irregular shapes.

State-of-the-art artificial intelligence and machine learning algorithms work well in simulated environments. But contact with objects in the real world often causes them to stumble. This happens because physical contact is often hard to model and even harder to control. Although a human can easily perform these tasks, there are significant technical hurdles for household robots to achieve the human ability to manipulate objects.

Robots struggle with two aspects of object manipulation: control and sensing. Many pick-and-place manipulator robots like those on assembly lines are equipped with a simple gripper or specialized tools dedicated only to certain tasks such as picking up and transporting a particular part. They often have difficulty manipulating objects with irregular shapes or elastic materials, particularly because they lack the effective force, or haptic feedback, that humans are naturally endowed with. Building a general-purpose robot hand with flexible fingers remains technically challenging and expensive.

It’s also worth mentioning that traditional manipulator robots require a stable platform to operate accurately, but accuracy drops dramatically when used with platforms that move, especially on a variety of surfaces. The coordination of locomotion and manipulation in a mobile robot is an open problem in the robotics community that needs to be solved before widely capable household robots can hit the market.

They love structure

In an assembly line or a warehouse, the environment and the sequence of tasks are strictly organized. This allows engineers to pre-program robot movements or use simple methods like QR codes to locate objects or target locations. However, household items are often disorganized and placed haphazardly.

Domestic robots have to deal with many uncertainties in their workspaces. The robot must first locate and identify the target object among many others. Very often it is also necessary to clear or avoid other obstacles in the workspace to be able to reach the item and perform given tasks. This requires the robot to have an excellent perception system, efficient navigation skills, and powerful and precise manipulation ability.

For example, robot vacuum users know to remove all small furniture and other obstacles such as cables from the floor, because even the best robot vacuum can’t remove them on its own. Even more difficult, the robot must operate in the presence of moving obstacles when people and pets walk nearby.

keep it simple

Although they seem simple for humans, many household chores are too complex for robots. Industrial robots are excellent for repetitive operations where the motion of the robot can be pre-programmed. But chores are often unique to the situation and can be full of surprises that require the robot to constantly make decisions and change its route in order to complete the tasks.

Consider cooking or washing dishes. During a few minutes of cooking, you can grab a sauté pan, a spatula, a stove knob, a fridge door handle, an egg and a bottle of cooking oil. To wash a pan, you typically hold and move it with one hand while scrubbing with the other, and make sure all cooked food residue is removed, then all soap is rinsed away.

There has been significant development in recent years using machine learning to train robots to make intelligent decisions when selecting and placing different objects, which means grabbing and moving objects from place to place. other. However, being able to train robots to master all different types of kitchen utensils and appliances would be another level of difficulty for even the best learning algorithms.

Not to mention that people’s homes often have stairs, narrow passages and high shelves. These hard-to-reach spaces limit the use of today’s mobile robots, which tend to use wheels or four legs. Humanoid robots, which would correspond more closely to the environments that humans construct and organize for themselves, have yet to be used reliably outside of laboratory environments.

One solution to the complexity of tasks is to build special-purpose robots, such as robot vacuums or food processors. Many different types of such devices are likely to be developed in the near future. However, I believe that general-purpose household robots are still a long way off.The conversation

Ayonga Hereidassistant professor of mechanical and aerospace engineering, The Ohio State University

This article is republished from The Conversation under a Creative Commons license. Read the original article.

‘, ‘window.fbAsyncInit = function() {‘, ‘FB.init({‘, ‘appId:’216372371876365′,’, ‘xfbml:true,’, ‘version: ‘v2.6” , ‘});’ ]; ppLoadLater.placeholderFBSDK.push(‘};’); var ppFacebookSDK= [
‘(function(d, s, id) {‘,
‘var js, fjs = d.getElementsByTagName(s)[0];’, ‘if (d.getElementById(id)) return;’, ‘js = d.createElement(s); js.id = id;’, ‘js.src = “https://connect.facebook.net/en_US/sdk.js”;’, ‘fjs.parentNode.insertBefore(js, fjs);’, ‘}( document, ‘script’, ‘facebook-jssdk’));’ ]; ppLoadLater.placeholderFBSDK = ppLoadLater.placeholderFBSDK.concat(ppFacebookSDK); ppLoadLater.placeholderFBSDK.push(‘‘); ppLoadLater.placeholderFBSDK = ppLoadLater.placeholderFBSDK.join(“n”);